A Measure of Association for Nonparametric Statistics

A number of x2 based nonparametric tests are used to determine the level of statistical significance. Once the significance level is determined with x2, Cramer's V can be used to measure the strength of association. Values for the maximum possible x2 are given for six nonparametric tests in order to facilitate the computation of an extension of V denoted as V'. An example is given where V' is applied to a one-way analysis of variance test for ranked data. Chi square based measures of association have been applied almost exclusively to nominal level contingency tables. The most often used x2 based measure of association is Cramer's